Using correlative data analysis to develop weather index that estimates the risk of forest fires in Lebanon & Mediterranean: Assessment versus prevalent meteorological indices

TitreUsing correlative data analysis to develop weather index that estimates the risk of forest fires in Lebanon & Mediterranean: Assessment versus prevalent meteorological indices
Type de publicationArticle de revue
Année de publication2017
Titre de la revueCase Studies in Fire Safety
Volume7
Pagination8 - 22
Auteur(s)Hamadeh, N., Karouni A., Daya B. et Chauvet P.
EditeurElsevier
Numéro ISSN2214-398X
Mots-clésCorrelation techniques, Data analysis, Fire danger index, Forest fire prediction
Résumé

Forest fires are among the most dangerous natural threats that bring calamities to a community and can turn it totally upside down. In this paper, to enable a prevention mechanism, we rely on analytics to build a novel fire danger index model that predicts the risk of a developing fire in north Lebanon. We use correlation methods such as statistical regression, Pearson, Spearman and Kendall’s Tau correlation to identify the most affecting parameters on fire ignition during the last six years in north Lebanon. The correlations of these attributes with fire occurrence are studied in order to develop the fire danger index. The strongly correlated attributes are then derived. We rely on linear regression to model the fire index as function of a reduced set of weather parameters that are easy to measure. This is critical as it facilitates the application of such prevention models in developing countries like Lebanon. The outcomes resulting from validation tests of the proposed index show high performance in the Lebanese regions. An assessment versus common widespread weather models is then made and has showed the significance the selected parameters. It is strongly believed that this index will help improve the ability of fire prevention measures in the Mediterranean basin area.

URLhttp://www.sciencedirect.com/science/article/pii/S2214398X16300127
DOI10.1016/j.csfs.2016.12.001